About this document

Spatio-Temporal Demand Prediction Model by Ishrat Jahan is a document available to read on EtoBox.

This document proposes a novel deep learning model called 1D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) combined into an end-to-end structure (1DConv-LSTM) to improve demand prediction for ride-sourcing using spatio-temporal data. The model was tested on real ride-hailing data from two Chinese cities and outperformed baseline models in prediction precision and computing efficiency. The document reviews previous work applying time-series analysis and deep learning to travel demand f

Author

Ishrat Jahan

Language

EN